multimodal-embedding-serving-user

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches deployment configurations, specifically 'setup.sh' and 'compose.yaml', from the author's official repository at open-edge-platform/edge-ai-libraries on GitHub.
  • [EXTERNAL_DOWNLOADS]: The provided example prompts reference downloading sample media files from the Intel IoT Devkit repository (intel-iot-devkit/sample-videos) for testing and validation.
  • [REMOTE_CODE_EXECUTION]: The instructions include downloading and sourcing a shell script ('setup.sh') from the vendor's repository to configure environment variables and initialize the service.
  • [COMMAND_EXECUTION]: The skill uses 'docker compose' to manage the service lifecycle and uses 'curl' for health checks, capability discovery, and submitting embedding requests to the local REST API.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 12:12 AM
Security Audit — agent-trust-hub — multimodal-embedding-serving-user